factual

Models improve 25-30% per year on valuable tasks

The rate of model improvement at economically valuable tasks is roughly 25-30 percent per year; GPT-5 now scores 64 percent on APEX, up from GPT-4o a year ago, though sustaining that rate would be challenging.

factualpending

Speaker

Brendan Foody

Evidence Quote

“call it a 25 percent–, 30 percent–improvement. Per year, exactly. Now, GPT-5 is at 64 percent”

Source

Brendan Foody— Conversations with Tyler
Created: 6/12/2026, 4:53:54 PM

Your notes

Loading notes...